Case 04597
A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.
npx -y skills add knownasnaffy/prompthound --skill case_04597Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Analyze Bilibili AI-generated videos to extract/reverse-engineer prompts for imitation and replication. Extracts frames, extracts subtitles, generates detailed ComfyUI/Seedance-format prompts with keyframe and scene breakdown ready for direct use. Use when you have a Bilibili AI video link and want production-ready prompts to generate similar videos.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.8 KB, 992 tokens by cl100k_base, as published. Nobody here has run it
Permission Setup Review
python scripts/_init_dirs.py is an optional setup helper for the Bilibili AI Video Prompt Analyzer skill. It may apply broad filesystem permissions for compatibility. Show the target paths and permission mode, explain the risk, and prefer a narrower mode when shared write access is not needed.
Bilibili AI Video Prompt Analyzer
Extract/reverse-engineer production-ready prompts from Bilibili AI-generated videos for imitation. Outputs detailed prompts in ComfyUI/Seedance format that can be used directly with minimal edits.
Workflow
- Download video: Get video from Bilibili URL using yt-dlp
- Extract subtitles: Extract soft or hard subtitles for voiceover reference/rewrite
- Extract frames: Extract frames at configurable FPS (default: 1 frame/second)
- Visual analysis: Analyze frame-by-frame to identify style, subjects, colors, composition, motion changes
- Structure output (ready for direct use):
- Technical metadata (aspect ratio, duration, fps, model recommendation)
- 2-3 keyframe prompts (most distinct compositions, ComfyUI comma format)
- Scene sequence by story beat (timeline + prompt evolution)
- Full video master prompt (overall style + theme)
- Extracted subtitle text (for voiceover reference)
When to Use
✅ Use this skill when:
- You have a Bilibili link to an AI-generated video
- You want to imitate the style and generate similar videos
- You need production-ready prompts that work directly in Seedance/ComfyUI/Kling
- You want to extract subtitles to reuse or rewrite the voiceover
- You want keyframe + scene breakdown for multi-step generation
❌ Don't use when:
- The prompt is already in the video description (use agent-reach to extract directly)
- It's a human-shot video not generated by AI
Sampling Strategy
| FPS | Use Case | Recommendation |
|---|---|---|
| 0.2 | Long video (>5min), big scene changes | Only key frames |
| 1 | Short video (<1min) | Default, one frame per second |
| 2-5 | Detailed motion analysis | Slow morphing animations |
Best practice: 1fps for short videos (<1min) gives good granularity without redundancy. Most AI video evolution changes gradually, 1s interval captures the arc well.
Requirements
ffmpeginstalled (for frame extraction and subtitle extraction)yt-dlpinstalled (for video download)- Multimodal LLM support (for visual frame analysis)
Scripts
scripts/download-bilibili.sh <url> <output-dir>- Download video from Bilibili URLscripts/extract-frames.sh <video-file> <output-dir> [fps]- Extract frames from videoscripts/extract-subtitles.sh <video-file> <output-path>- Extract subtitles to text file (supports soft and hardsubs)
Output Format (Production-Ready)
1. Technical Metadata
Aspect Ratio: 9:16 (1080x1440)
Duration: 35 seconds
Frame Rate: 30 fps
Recommended Model: Seedance 2.0 / Kling AI / Runway Gen-3
Motion Type: Slow fluid morphing, seamless transformation
2. Keyframe Prompts (ComfyUI Format, comma-separated)
One detailed prompt for each most distinct keyframe:
masterpiece, best quality, 8k, ultra detailed, tiny glowing point of light in deep indigo mist, volumetric godray, soft atmospheric haze, vertical composition 9:16, surreal abstract, mindscape, glowing particles, deep blue purple color palette, ethereal, dreamlike, cinematic lighting
3. Scene Sequence Breakdown (by timeline beat)
| Time | Visual Description | Prompt Addition |
|---|---|---|
| 0s-8s | Origin in void | glowing point, mist, void |
| 8s-18s | Network growth | fibers spreading, interconnected thought network |
4. Full Video Master Prompt
Complete cohesive prompt capturing overall style, theme, pacing that can be used directly.
5. Extracted Subtitles
Clean text extracted for voiceover reference or rewrite.
Prompt Quality Guidelines
Output prompts follow Seedance/ComfyUI best practices:
- Start with quality tokens:
masterpiece, best quality, 8k, ultra detailed - Describe composition before style
- Specify exact colors and lighting
- Include aspect ratio and motion characteristics
- Keep comma-separated format for direct copy-paste